Commit 9a9fa2f0 authored by Chengchang Tang's avatar Chengchang Tang Committed by Zheng Zengkai
Browse files

RDMA/hns: Fix level-0 addressing for huge page 

driver inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I5Y79T



-------------------------------------------------------------------

Currently, when creating a MR, there is a certain probability of
causing a hardware exception when addressing at level 0 with a huge
page. This is because the PA address is now aligned to 4K instead of
the actual page size set by the driver.

When the MTR of multiple regions is addressed at level 0 with a huge
page, multiple regions will share the same huge page. This huge page
will be divided into multiple 4K pages, and these pages will be
allocated to different regions. At this point, all the regions of this
MTR only require 4k alignment instead of the actual pagesize. This can
help reduce memory consumption.

But when there is only one region, the MTR with level-0 addressing can
directly use this huge page. At this point the hardware needs this page
to be aligned to the actual page size, not 4K.

This patch set page size to 4k only when the MTR with level 0 addressing
has mutliple regions.

Fixes: 0e0ab04b ("RDMA/hns: Refactor the MTR creation flow")
Signed-off-by: default avatarChengchang Tang <tangchengchang@huawei.com>
Reviewed-by: default avatarYangyang Li <liyangyang20@huawei.com>
Reviewed-by: default avatarYueHaibing <yuehaibing@huawei.com>
Signed-off-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
parent cf2f2029

drivers/infiniband/hw/hns/hns_roce_mr.c

+14 −10
Original line number Original line Diff line number Diff line
@@ -712,6 +712,16 @@ static int cal_mtr_pg_cnt(struct hns_roce_mtr *mtr) 
	return page_cnt;

	return page_cnt;

}

}





static bool need_split_huge_page(struct hns_roce_mtr *mtr)

{

	/* When HEM buffer uses 0-level addressing, the page size is

	 * equal to the whole buffer size. If the current MTR has multiple

	 * regions, we split the buffer into small pages(4k, required by hns

	 * ROCEE). These pages will be used in multiple regions.

	 */

	return mtr->hem_cfg.is_direct && mtr->hem_cfg.region_count > 1;

}



static int mtr_map_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr)

static int mtr_map_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr)

{

{

	struct ib_device *ibdev = &hr_dev->ib_dev;

	struct ib_device *ibdev = &hr_dev->ib_dev;
@@ -721,13 +731,7 @@ static int mtr_map_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr) 
	int npage;

	int npage;

	int ret;

	int ret;





	/* When HEM buffer uses 0-level addressing, the page size is

	page_shift = need_split_huge_page(mtr) ? HNS_HW_PAGE_SHIFT :

	 * equal to the whole buffer size, and we split the buffer into

	 * small pages which is used to check whether the adjacent

	 * units are in the continuous space and its size is fixed to

	 * 4K based on hns ROCEE's requirement.

	 */

	page_shift = mtr->hem_cfg.is_direct ? HNS_HW_PAGE_SHIFT :

						 mtr->hem_cfg.buf_pg_shift;

						 mtr->hem_cfg.buf_pg_shift;

	/* alloc a tmp array to store buffer's dma address */

	/* alloc a tmp array to store buffer's dma address */

	pages = kvcalloc(page_count, sizeof(dma_addr_t), GFP_KERNEL);

	pages = kvcalloc(page_count, sizeof(dma_addr_t), GFP_KERNEL);
@@ -748,7 +752,7 @@ static int mtr_map_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr) 
		goto err_alloc_list;

		goto err_alloc_list;

	}

	}





	if (mtr->hem_cfg.is_direct && npage > 1) {

	if (need_split_huge_page(mtr) && npage > 1) {

		ret = mtr_check_direct_pages(pages, npage, page_shift);

		ret = mtr_check_direct_pages(pages, npage, page_shift);

		if (ret) {

		if (ret) {

			ibdev_err(ibdev, "failed to check %s page: %d / %d.\n",

			ibdev_err(ibdev, "failed to check %s page: %d / %d.\n",
@@ -1026,7 +1030,7 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev, 
	cfg->is_direct = !mtr_has_mtt(attr);

	cfg->is_direct = !mtr_has_mtt(attr);

	cfg->region_count = attr->region_count;

	cfg->region_count = attr->region_count;

	buf_size = mtr_bufs_size(attr);

	buf_size = mtr_bufs_size(attr);

	if (cfg->is_direct) {

	if (need_split_huge_page(mtr)) {

		buf_pg_sz = HNS_HW_PAGE_SIZE;

		buf_pg_sz = HNS_HW_PAGE_SIZE;

		cfg->buf_pg_count = 1;

		cfg->buf_pg_count = 1;

		/* The ROCEE requires the page size to be 4K * 2 ^ N. */

		/* The ROCEE requires the page size to be 4K * 2 ^ N. */